Reducing Drift in Visual Odometry by Inferring Sun Direction Using a
Bayesian Convolutional Neural Network

v1v2v3v4v5 (latest)

Reducing Drift in Visual Odometry by Inferring Sun Direction Using a Bayesian Convolutional Neural Network

20 September 2016

Valentin Peretroukhin

ArXiv (abs)PDF HTML

Papers citing "Reducing Drift in Visual Odometry by Inferring Sun Direction Using a Bayesian Convolutional Neural Network"

10 / 10 papers shown

Title
PROBE-GK: Predictive Robust Estimation using Generalized Kernels Valentin Peretroukhin William Vega-Brown Nicholas Roy Jonathan Kelly OOD 71 18 0 01 Aug 2017
Improving the Accuracy of Stereo Visual Odometry Using Visual Illumination Estimation Lee Clement Valentin Peretroukhin Jonathan Kelly 24 6 0 15 Sep 2016
Direct Sparse Odometry Jakob Engel V. Koltun Daniel Cremers 99 2,531 0 09 Jul 2016
Noise Models in Feature-based Stereo Visual Odometry P. Alcantarilla Oliver J. Woodford 3DV 21 3 0 01 Jul 2016
Find your Way by Observing the Sun and Other Semantic Cues Wei-Chiu Ma Shenlong Wang Marcus A. Brubaker Sanja Fidler R. Urtasun 82 42 0 23 Jun 2016
Modelling Uncertainty in Deep Learning for Camera Relocalization Alex Kendall R. Cipolla BDL 74 541 0 19 Sep 2015
Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference Y. Gal Zoubin Ghahramani UQCV BDL 311 751 0 06 Jun 2015
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 909 9,364 0 06 Jun 2015
Going Deeper with Convolutions Christian Szegedy Wei Liu Yangqing Jia P. Sermanet Scott E. Reed Dragomir Anguelov D. Erhan Vincent Vanhoucke Andrew Rabinovich 505 43,717 0 17 Sep 2014
Caffe: Convolutional Architecture for Fast Feature Embedding Yangqing Jia Evan Shelhamer Jeff Donahue Sergey Karayev Jonathan Long Ross B. Girshick S. Guadarrama Trevor Darrell VLM BDL 3DV 300 14,717 0 20 Jun 2014

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.